© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 5009
    Prev
    Next
    INDEX
    Explanations

    the word "Therefore" in texts, possibly indicating a logical conclusion or consequence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "therefore" indicating conclusions or logical links in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rumble
    -0.69
    Fram
    -0.59
     Feld
    -0.58
     sights
    -0.57
     Aboriginal
    -0.56
     Tacoma
    -0.56
     Defenders
    -0.55
     NL
    -0.54
     Rocky
    -0.54
     nurs
    -0.53
    POSITIVE LOGITS
    forth
    1.16
    ommel
    0.80
     guiActiveUn
    0.78
    xual
    0.77
    tainment
    0.73
    manuel
    0.71
    atto
    0.70
     arose
    0.69
    oner
    0.69
    ptions
    0.68
    Activations Density 0.033%

    No Known Activations